File size: 5,491 Bytes
a8b3f00 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 |
import os
from collections.abc import Generator
import pytest
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
from core.model_runtime.entities.message_entities import (
AssistantPromptMessage,
PromptMessageTool,
SystemPromptMessage,
UserPromptMessage,
)
from core.model_runtime.errors.validate import CredentialsValidateFailedError
from core.model_runtime.model_providers.localai.llm.llm import LocalAILanguageModel
def test_validate_credentials_for_chat_model():
model = LocalAILanguageModel()
with pytest.raises(CredentialsValidateFailedError):
model.validate_credentials(
model="chinese-llama-2-7b",
credentials={
"server_url": "hahahaha",
"completion_type": "completion",
},
)
model.validate_credentials(
model="chinese-llama-2-7b",
credentials={
"server_url": os.environ.get("LOCALAI_SERVER_URL"),
"completion_type": "completion",
},
)
def test_invoke_completion_model():
model = LocalAILanguageModel()
response = model.invoke(
model="chinese-llama-2-7b",
credentials={
"server_url": os.environ.get("LOCALAI_SERVER_URL"),
"completion_type": "completion",
},
prompt_messages=[UserPromptMessage(content="ping")],
model_parameters={"temperature": 0.7, "top_p": 1.0, "max_tokens": 10},
stop=[],
user="abc-123",
stream=False,
)
assert isinstance(response, LLMResult)
assert len(response.message.content) > 0
assert response.usage.total_tokens > 0
def test_invoke_chat_model():
model = LocalAILanguageModel()
response = model.invoke(
model="chinese-llama-2-7b",
credentials={
"server_url": os.environ.get("LOCALAI_SERVER_URL"),
"completion_type": "chat_completion",
},
prompt_messages=[UserPromptMessage(content="ping")],
model_parameters={"temperature": 0.7, "top_p": 1.0, "max_tokens": 10},
stop=[],
user="abc-123",
stream=False,
)
assert isinstance(response, LLMResult)
assert len(response.message.content) > 0
assert response.usage.total_tokens > 0
def test_invoke_stream_completion_model():
model = LocalAILanguageModel()
response = model.invoke(
model="chinese-llama-2-7b",
credentials={
"server_url": os.environ.get("LOCALAI_SERVER_URL"),
"completion_type": "completion",
},
prompt_messages=[UserPromptMessage(content="Hello World!")],
model_parameters={"temperature": 0.7, "top_p": 1.0, "max_tokens": 10},
stop=["you"],
stream=True,
user="abc-123",
)
assert isinstance(response, Generator)
for chunk in response:
assert isinstance(chunk, LLMResultChunk)
assert isinstance(chunk.delta, LLMResultChunkDelta)
assert isinstance(chunk.delta.message, AssistantPromptMessage)
assert len(chunk.delta.message.content) > 0 if chunk.delta.finish_reason is None else True
def test_invoke_stream_chat_model():
model = LocalAILanguageModel()
response = model.invoke(
model="chinese-llama-2-7b",
credentials={
"server_url": os.environ.get("LOCALAI_SERVER_URL"),
"completion_type": "chat_completion",
},
prompt_messages=[UserPromptMessage(content="Hello World!")],
model_parameters={"temperature": 0.7, "top_p": 1.0, "max_tokens": 10},
stop=["you"],
stream=True,
user="abc-123",
)
assert isinstance(response, Generator)
for chunk in response:
assert isinstance(chunk, LLMResultChunk)
assert isinstance(chunk.delta, LLMResultChunkDelta)
assert isinstance(chunk.delta.message, AssistantPromptMessage)
assert len(chunk.delta.message.content) > 0 if chunk.delta.finish_reason is None else True
def test_get_num_tokens():
model = LocalAILanguageModel()
num_tokens = model.get_num_tokens(
model="????",
credentials={
"server_url": os.environ.get("LOCALAI_SERVER_URL"),
"completion_type": "chat_completion",
},
prompt_messages=[
SystemPromptMessage(
content="You are a helpful AI assistant.",
),
UserPromptMessage(content="Hello World!"),
],
tools=[
PromptMessageTool(
name="get_current_weather",
description="Get the current weather in a given location",
parameters={
"type": "object",
"properties": {
"location": {"type": "string", "description": "The city and state e.g. San Francisco, CA"},
"unit": {"type": "string", "enum": ["c", "f"]},
},
"required": ["location"],
},
)
],
)
assert isinstance(num_tokens, int)
assert num_tokens == 77
num_tokens = model.get_num_tokens(
model="????",
credentials={
"server_url": os.environ.get("LOCALAI_SERVER_URL"),
"completion_type": "chat_completion",
},
prompt_messages=[UserPromptMessage(content="Hello World!")],
)
assert isinstance(num_tokens, int)
assert num_tokens == 10
|